← Back to community benchmarks

Qwen3.6-27B-OptiQ

M3 Pro (18c) · 36 GB · 4bit · 2026-06-15

Performance

1k

tokens

94.3

PP tok/s

7.5

TG tok/s

10863

TTFT (ms)

18.7

Peak mem (GB)

Hardware

Chip M3 Pro (18c)

Memory 36 GB

GPU Cores 18

Software

oMLX v0.4.4rc1

macOS macOS 26.5.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	94.3	7.5	18.7 GB	current
4k	97.4	7.4	20.1 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	7.5	1.00×
2×	14.7	1.96×
4×	29.2	3.89×